© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 16295
    Prev
    Next
    INDEX
    Explanations

    code documentation and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ീ
    1.66
    mals
    1.64
    ิน
    1.60
    il
    1.58
     graça
    1.57
    l
    1.57
    为
    1.56
    ันทร์
    1.56
     exclamation
    1.55
    Ш
    1.55
    POSITIVE LOGITS
    к
    1.88
    urethane
    1.76
    ી
    1.75
    जिये
    1.72
    ি
    1.66
    ेक्स
    1.65
     digitar
    1.63
    스트
    1.63
    畊
    1.62
     meningkatkan
    1.62
    Activations Density 0.028%

    No Known Activations